Caesar AI Atlas

Self-supervised Learning

Also known as: Self supervised Learning

Caesar AI Atlas Definition

Self-supervised learning is a machine learning approach that creates training signals from unlabeled data itself. It converts aspects of an unsupervised problem into supervised learning by generating surrogate labels, making it useful when labeled data is scarce but unlabeled data is abundant.

Other Definitions

Self-supervised Learning Source

A family of techniques for converting an unsupervised machine learning problem into a supervised machine learning problem by creating surrogate labels from unlabeled examples. Some Transformer-based models such as BERT use self-supervised learning. Self-supervised training is a semi-supervised learning approach.

Also Referenced In

Concept Comparisons

Related Terms